© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93734
    Prev
    Next
    INDEX
    Explanations

    percent signs and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    捨
    -0.93
    <bos>
    -0.90
     soon
    -0.85
     envision
    -0.84
     need
    -0.82
     Revised
    -0.81
    手順
    -0.80
     probably
    -0.79
     versions
    -0.79
     Well
    -0.78
    POSITIVE LOGITS
     $\%
    1.06
     PERCENT
    1.06
    ٪
    1.05
    percent
    1.05
     $\%$
    1.04
     eau
    1.02
    YAML
    1.02
    -%
    0.98
     percent
    0.98
     Percent
    0.96
    Activations Density 0.030%

    No Known Activations